library(tidyverse)
-- Attaching packages --------------------------------------------------------------------------------------------- tidyverse 1.2.1 --
v ggplot2 3.1.0 v purrr 0.2.5
v tibble 1.4.2 v dplyr 0.7.8
v tidyr 0.8.2 v stringr 1.3.1
v readr 1.1.1 v forcats 0.3.0
-- Conflicts ------------------------------------------------------------------------------------------------ tidyverse_conflicts() --
x dplyr::filter() masks stats::filter()
x dplyr::lag() masks stats::lag()
library(cowplot)
Attaching package: 'cowplot'
The following object is masked from 'package:ggplot2':
ggsave
library(GGally)
Attaching package: 'GGally'
The following object is masked from 'package:dplyr':
nasa
library(heatmaply)
Loading required package: plotly
Attaching package: 'plotly'
The following object is masked from 'package:ggplot2':
last_plot
The following object is masked from 'package:stats':
filter
The following object is masked from 'package:graphics':
layout
Loading required package: viridis
Loading required package: viridisLite
======================
Welcome to heatmaply version 0.15.2
Type citation('heatmaply') for how to cite the package.
Type ?heatmaply for the main documentation.
The github page is: https://github.com/talgalili/heatmaply/
Please submit your suggestions and bug-reports at: https://github.com/talgalili/heatmaply/issues
Or contact: <tal.galili@gmail.com>
======================
library(sva)
Loading required package: mgcv
Loading required package: nlme
Attaching package: 'nlme'
The following object is masked from 'package:dplyr':
collapse
This is mgcv 1.8-25. For overview type 'help("mgcv-package")'.
Loading required package: genefilter
Attaching package: 'genefilter'
The following object is masked from 'package:readr':
spec
Loading required package: BiocParallel
library(limma)
library(biobroom)
Loading required package: broom
library(ggridges)
Attaching package: 'ggridges'
The following object is masked from 'package:ggplot2':
scale_discrete_manual
# Cells #
vf.cell.neg.raw <- read_csv("./data/abundances/p5fa_vpa_exp_hilic_target_cells_negmode_abundances.csv")
Parsed with column specification:
cols(
.default = col_double(),
Samples = col_character(),
Mode = col_character(),
Type = col_character(),
Group = col_character(),
VPA = col_character(),
FA = col_character(),
Plate = col_character()
)
See spec(...) for full column specifications.
vf.cell.pos.raw <- read_csv("./data/abundances/p5fa_vpa_exp_hilic_target_cells_posmode_abundances.csv")
Parsed with column specification:
cols(
.default = col_double(),
Samples = col_character(),
Mode = col_character(),
Type = col_character(),
Group = col_character(),
VPA = col_character(),
FA = col_character(),
Plate = col_character()
)
See spec(...) for full column specifications.
# Media #
vf.med.neg.raw <- read_csv("./data/abundances/p5fa_vpa_exp_hilic_target_media_negmode_abundances.csv")
Parsed with column specification:
cols(
.default = col_double(),
Samples = col_character(),
Mode = col_character(),
Type = col_character(),
Group = col_character(),
VPA = col_character(),
FA = col_character(),
Plate = col_character()
)
See spec(...) for full column specifications.
vf.med.pos.raw <- read_csv("./data/abundances/p5fa_vpa_exp_hilic_target_media_posmode_abundances.csv")
Parsed with column specification:
cols(
.default = col_double(),
Samples = col_character(),
Mode = col_character(),
Type = col_character(),
Group = col_character(),
VPA = col_character(),
FA = col_character(),
Plate = col_character()
)
See spec(...) for full column specifications.
# Cells #
vf.cell.neg.compound.info <- read_csv("./data/compound_info/p5fa_vpa_exp_hilic_target_cells_negmode_cmpnd_info.csv")
Parsed with column specification:
cols(
compound_short = col_character(),
compound_full = col_character(),
formula = col_character(),
mass = col_double(),
rt = col_double(),
cas_id = col_character()
)
vf.cell.pos.compound.info <- read_csv("./data/compound_info/p5fa_vpa_exp_hilic_target_cells_posmode_cmpnd_info.csv")
Parsed with column specification:
cols(
compound_short = col_character(),
compound_full = col_character(),
formula = col_character(),
mass = col_double(),
rt = col_double(),
cas_id = col_character()
)
# Media #
vf.med.neg.compound.info <- read_csv("./data/compound_info/p5fa_vpa_exp_hilic_target_media_negmode_cmpnd_info.csv")
Parsed with column specification:
cols(
compound_short = col_character(),
compound_full = col_character(),
formula = col_character(),
mass = col_double(),
rt = col_double(),
cas_id = col_character()
)
vf.med.pos.compound.info <- read_csv("./data/compound_info/p5fa_vpa_exp_hilic_target_media_posmode_cmpnd_info.csv")
Parsed with column specification:
cols(
compound_short = col_character(),
compound_full = col_character(),
formula = col_character(),
mass = col_double(),
rt = col_double(),
cas_id = col_character()
)
# Kegg/other ID reference #
#cmpnd.id.db <- read_csv("./data/anp_db_compound_kegg.csv")
MissingPerSamplePlot <- function(raw.data, start.string) {
# Counts the number of missing/NA values per sample and
# percent compounds missing out of total number of compounds per sample
# Then passes the result into a vertical bar plot, where each
# bar represents a single sample and the size of the bar
# is the % of compounds missing
counted.na <- raw.data %>%
select(starts_with(start.string)) %>%
mutate(
count.na = apply(., 1, function(x) sum(is.na(x))),
percent.na = (count.na / ncol(raw.data %>% select(starts_with(start.string)))) * 100
) %>%
dplyr::select(count.na, percent.na) %>%
bind_cols(
raw.data %>%
select(Samples, Group)
) %>%
arrange(percent.na) %>%
mutate(f.order = factor(Samples, levels = Samples))
counted.na %>%
ggplot(aes(x = f.order, y = percent.na, fill = Group)) +
geom_bar(stat = "identity") +
geom_hline(yintercept = 20, color = "gray", size = 1, alpha = 0.8) +
coord_flip()+
xlab("Samples") +
ylab("Percent missing values in sample") +
theme(axis.text.y = element_text(size = 6))
}
MissingPerCompound <- function(raw.data, start.string){
# Function to count in how many experimental samples each compound is missing
# Also calculates the % missing:
# (# NA per compound across all experimental samples) * 100 / (tot num of samples)
raw.data %>%
filter(Group == "sample") %>%
select(Samples, starts_with(start.string)) %>%
gather(key = "Compound", value = "Abundance", -Samples) %>%
group_by(Compound) %>%
summarise(
na_count = sum(is.na(Abundance)),
n_samples = n(),
percent_na = (na_count * 100 / n_samples)
) %>%
filter(na_count > 0) %>%
arrange(desc(percent_na))
}
ReplaceNAwMinLogTransformMult <- function(raw.dataframe, start.prefix) {
# Function to replace any NAs in each column with the minimum for that column,
# separately for each sample type.
# NA in negative control samples are replaced by 2.
# Then data is log2 transformed
# experimental samples #
smpls <- raw.dataframe %>%
filter(Group == "sample") %>%
dplyr::select(starts_with(start.prefix))
smpls.min <- lapply(smpls, min, na.rm = TRUE)
smpls.noNA <- raw.dataframe %>%
filter(Group == "sample") %>%
dplyr::select(Samples:Plate) %>%
bind_cols(
smpls %>%
replace_na(replace = smpls.min) %>%
log2()
)
# QC samples #
QC <- raw.dataframe %>%
filter(Group == "mix") %>%
dplyr::select(starts_with(start.prefix))
QC.min <- lapply(QC, min, na.rm = TRUE)
# replace the missing values in the QC with the minimum of the QC
# then take the log
QC.noNA <- raw.dataframe %>%
filter(Group == "mix") %>%
dplyr::select(Samples:Plate) %>%
bind_cols(
QC %>%
replace_na(replace = QC.min) %>%
log2()
)
# not samples or QC #
other.min <- setNames(
as.list(
rep(2, ncol(
raw.dataframe %>%
dplyr::select(starts_with(start.prefix))))
),
colnames(raw.dataframe %>% dplyr::select(starts_with(start.prefix)))
)
other.num.log <- raw.dataframe %>%
filter(Group != "mix" & Group != "sample") %>%
dplyr::select(Samples:Plate) %>%
bind_cols(
raw.dataframe %>%
filter(Group != "mix" & Group != "sample") %>%
dplyr::select(starts_with(start.prefix)) %>%
replace_na(replace = other.min) %>%
log2()
)
all.noNA <- smpls.noNA %>%
bind_rows(QC.noNA) %>%
bind_rows(other.num.log)
}
HeatmapPrepAlt <- function(raw.data, start.prefix){
# function for preparing dara for heatmap viz
x <- raw.data %>%
select(starts_with(start.prefix)) %>%
scale(center = TRUE, scale = TRUE) %>%
as.matrix()
row.names(x) <- raw.data$Samples
return(x)
}
Q: What are the distributions of compound masses and retention times?
full.vf.cmpnd <- vf.cell.neg.compound.info %>%
mutate(Set = "Cells / Neg") %>%
bind_rows(vf.cell.pos.compound.info %>% mutate(Set = "Cells / Pos")) %>%
bind_rows(vf.med.neg.compound.info %>% mutate(Set = "Media / Neg")) %>%
bind_rows(vf.med.pos.compound.info %>% mutate(Set = "Media / Pos"))
full.vf.cmpnd %>%
ggplot(aes(x = rt, y = mass)) +
geom_point(size = 3, alpha = 0.3) +
xlab("Retention Time (min)") +
ylab("Mass (Da)") +
ggtitle("Mass v RT\nVPA + FA HILIC") +
ylim(0, 1000)
full.vf.cmpnd %>%
ggplot(aes(x = rt, y = mass, color = Set)) +
geom_point(size = 3, alpha = 0.8) +
xlab("Retnetion Time (min)") +
ylab("Mass (Da)") +
ggtitle("Mass v RT\nVPA + FA HILIC") +
facet_wrap(~ Set) +
ylim(0, 1000)
Q: Which compounds were found in one or more of the data types?
## cell join ##
vf.cell.cmpnd.join <- vf.cell.neg.compound.info %>%
inner_join(vf.cell.pos.compound.info, by = "cas_id", suffix = c(".c.n", ".c.p")) %>%
select(
contains("cas_id"), contains("short"),
contains("full"), starts_with("formula"),
starts_with("mass"), starts_with("rt")
)
# compound names - found in pos and neg mode / cells
print(vf.cell.cmpnd.join$compound_full.c.n)
[1] "Glycine"
[2] "Pyruvate"
[3] "Alanine"
[4] "Beta-Alanine"
[5] "Sarcosine"
[6] "2-Aminobutyric Acid"
[7] "BAIBA"
[8] "GABA"
[9] "Serine"
[10] "Hypotaurine"
[11] "Uracil"
[12] "Creatinine"
[13] "Proline"
[14] "Valine"
[15] "Threonine"
[16] "Homoserine"
[17] "Taurine"
[18] "Ketoleucine"
[19] "N-Acetylalanine"
[20] "Creatine"
[21] "Leucine"
[22] "Isoleucine"
[23] "Asparagine"
[24] "Ornithine"
[25] "Aspartic Acid"
[26] "Adenine"
[27] "Glutamine"
[28] "Lysine"
[29] "Glutamic Acid"
[30] "Methionine"
[31] "Xanthine"
[32] "4-Hydroxyphenylacetic Acid"
[33] "3-Sulfinoalanine"
[34] "Histidine"
[35] "Allantoin"
[36] "5-Hydroxylysine"
[37] "Phenylalanine"
[38] "Pyridoxal"
[39] "Pyridoxine"
[40] "Glycerol 2-Phosphate"
[41] "Arginine"
[42] "Tyrosine"
[43] "D-Galactitol"
[44] "D-Sorbitol"
[45] "Phosphocholine"
[46] "N-alpha-Acetyl-L-glutamine"
[47] "Tryptophan"
[48] "Pantothenic Acid"
[49] "Cystathionine"
[50] "Methyl Jasmonate"
[51] "Carnosine"
[52] "Cytidine"
[53] "Uridine"
[54] "D-Glucose 6-phosphate"
[55] "D-Fructose 6-phosphate"
[56] "Thiamine (Vit B1)"
[57] "Inosine"
[58] "Guanosine"
[59] "Ophthalmic Acid"
[60] "5'-Methylthioadenosine"
[61] "N-Acetylaspartyl Glutamic Acid"
[62] "Glutathione (GSH)"
[63] "N-Acetylneuraminic Acid"
[64] "UMP"
[65] "3-Phosphoglyceroinositol"
[66] "AMP"
[67] "S-Adenosylhomocysteine (SAH)"
[68] "CDP"
[69] "ADP"
[70] "GDP"
[71] "UTP"
[72] "ATP"
[73] "GTP"
[74] "Cyclic adenosine diphosphate ribose (cADP-ribose)"
[75] "UDP-N-Acetylgalactosamine"
[76] "GSSG"
[77] "NAD"
[78] "NADH"
[79] "NADP"
[80] "Flavin adenine dinucleotide (FAD)"
[81] "Acetyl-CoA"
# percent of cell / neg compounds found in cell / pos
round(nrow(vf.cell.cmpnd.join) * 100 / nrow(vf.cell.neg.compound.info), 1)
[1] 58.3
# percent of cell / neg compounds found in cell / pos
round(nrow(vf.cell.cmpnd.join) * 100 / nrow(vf.cell.pos.compound.info), 1)
[1] 56.2
vf.cell.cmpnd.join %>%
select(contains("mass")) %>%
ggpairs()
vf.cell.cmpnd.join %>%
select(starts_with("rt")) %>%
ggpairs()
### Media join ###
vf.med.cmpnd.join <- vf.med.neg.compound.info %>%
inner_join(vf.med.pos.compound.info, by = "cas_id", suffix = c(".m.n", ".m.p")) %>%
select(
contains("cas_id"), contains("short"),
contains("full"), starts_with("formula"),
starts_with("mass"), starts_with("rt")
)
# compound names - found in pos and neg mode / media
print(vf.med.cmpnd.join$compound_full.m.n)
[1] "Alanine" "Serine" "Creatinine"
[4] "Proline" "Valine" "Threonine"
[7] "Taurine" "Creatine" "Leucine"
[10] "Isoleucine" "Glutamine" "Lysine"
[13] "Glutamic Acid" "Methionine" "Histidine"
[16] "Allantoin" "Phenylalanine" "Pyridoxine"
[19] "Arginine" "Citrulline" "Tyrosine"
[22] "D-Sorbitol" "Tryptophan" "Pantothenic Acid"
[25] "Thiamine (Vit B1)"
# percent of media / neg compounds found in media / pos
round(nrow(vf.med.cmpnd.join) * 100 / nrow(vf.med.neg.compound.info), 1)
[1] 44.6
# percent of media / pos compounds found in media / neg
round(nrow(vf.med.cmpnd.join) * 100 / nrow(vf.med.pos.compound.info), 1)
[1] 53.2
# vf all match
vf.all.cmpnd.join <- vf.cell.cmpnd.join %>%
inner_join(vf.med.cmpnd.join, by = "cas_id") %>%
select(
contains("cas_id"), contains("short"),
contains("full"), starts_with("formula"),
starts_with("mass"), starts_with("rt")
)
nrow(vf.all.cmpnd.join)
[1] 24
vf.all.cmpnd.join %>%
select(contains("mass")) %>%
ggpairs()
vf.all.cmpnd.join %>%
select(starts_with("rt")) %>%
ggpairs()
Q: Do any of the samples have greater than 20% missing (NA) compound abundances, out of all of the features in the dataset?
MissingPerSamplePlot(vf.cell.neg.raw, "hVPA_FAnC") +
ggtitle("Missing Per Sample\nVPA + FA HILIC / Cells / Neg Mode")
MissingPerSamplePlot(vf.cell.pos.raw, "hVPA_FApC") +
ggtitle("Missing Per Sample\nVPA + FA HILIC / Cells / Pos Mode")
MissingPerSamplePlot(vf.med.neg.raw, "hVPA_FAnM") +
ggtitle("Missing Per Sample\nVPA + FA HILIC / Media / Neg Mode")
MissingPerSamplePlot(vf.med.pos.raw, "hVPA_FApM") +
ggtitle("Missing Per Sample\nVPA + FA HILIC / Media / Pos Mode")
Q: Are any of the compounds more than 20% missing in the experimental sample group? If there are any, they will be excluded from analysis.
(vf.cell.neg.cmpnd.to.excl <- MissingPerCompound(vf.cell.neg.raw, "hVPA_FAnC") %>%
filter(percent_na > 20))
# A tibble: 5 x 4
Compound na_count n_samples percent_na
<chr> <int> <int> <dbl>
1 hVPA_FAnC139 14 22 63.6
2 hVPA_FAnC72 8 22 36.4
3 hVPA_FAnC113 7 22 31.8
4 hVPA_FAnC138 5 22 22.7
5 hVPA_FAnC64 5 22 22.7
MissingPerCompound(vf.cell.pos.raw, "hVPA_FApC") %>%
filter(percent_na > 20)
# A tibble: 0 x 4
# ... with 4 variables: Compound <chr>, na_count <int>, n_samples <int>,
# percent_na <dbl>
MissingPerCompound(vf.med.neg.raw, "hVPA_FAnM") %>%
filter(percent_na > 20)
# A tibble: 0 x 4
# ... with 4 variables: Compound <chr>, na_count <int>, n_samples <int>,
# percent_na <dbl>
MissingPerCompound(vf.med.pos.raw, "hVPA_FApM") %>%
filter(percent_na > 20)
# A tibble: 0 x 4
# ... with 4 variables: Compound <chr>, na_count <int>, n_samples <int>,
# percent_na <dbl>
vf.cell.neg.raw.grp.mean <- vf.cell.neg.raw %>%
group_by(Group) %>%
summarize_at(vars(matches("hVPA_FAnC")), mean, na.rm = TRUE) %>%
gather(key = "Compound", value = "Grp_mean_abun", -Group)
vf.cell.neg.raw.grp.mean %>%
ggplot(aes(log2(Grp_mean_abun), color = Group)) +
geom_density(size = 2, alpha = 0.8) +
ggtitle("Distribution of compound means\nVPA + FA HILIC / Cells / Negative Mode\nGrouped by sample type")
vf.cell.neg.raw.grp.mean.order <- vf.cell.neg.raw.grp.mean %>%
filter(Group == "sample") %>%
arrange(Grp_mean_abun)
vf.cell.neg.raw %>%
select(Samples, Group, starts_with("hVPA_FAnC")) %>%
gather("Compound", value = "Abundance", -c(Samples, Group)) %>%
mutate(Cmpnd_sort = factor(Compound, levels = vf.cell.neg.raw.grp.mean.order$Compound)) %>%
ggplot(aes(Cmpnd_sort, log2(Abundance), color = Group, group = Samples)) +
geom_line(alpha = 0.1, size = 1) +
theme(axis.text.x = element_blank(), axis.ticks.x = element_blank()) +
xlab("Compound") +
geom_line(
data = vf.cell.neg.raw.grp.mean %>%
mutate(Cmpnd_sort = factor(Compound, levels = vf.cell.neg.raw.grp.mean.order$Compound)),
aes(Cmpnd_sort, log2(Grp_mean_abun), color = Group, group = Group),
size = 0.5
) +
ggtitle("Profile Plot of all compound abundances\nWith average per sample type overlaid\nVPA + FA HILIC/ Cells / Negative Mode")
vf.cell.neg.raw.grp.mean %>%
mutate(Cmpnd_sort = factor(Compound, levels = vf.cell.neg.raw.grp.mean.order$Compound)) %>%
ggplot(aes(Cmpnd_sort, log2(Grp_mean_abun), color = Group, group = Group)) +
geom_point(size = 1, alpha = 0.8) +
geom_line(alpha = 0.8) +
theme(axis.text.x = element_blank(), axis.ticks.x = element_blank()) +
xlab("Compound") +
ylab("log2(Sample Type Mean)") +
ggtitle("Profile Plot of compound means by sample type only\nVPA + FA HILIC / Cells / Negative Mode")
vf.cell.neg.raw.grp.diff <- vf.cell.neg.raw.grp.mean %>%
spread(Group, Grp_mean_abun) %>%
mutate(
smpl_solv_diff = sample / solv,
)
vf.cell.neg.raw.grp.diff %>%
ggplot(aes(log2(smpl_solv_diff))) +
geom_histogram(bins = 50)
vf.cell.neg.cmpnd.to.incl <- vf.cell.neg.raw.grp.diff %>%
filter(smpl_solv_diff > 2.5 | is.na(smpl_solv_diff)) %>%
filter(!(Compound %in% vf.cell.neg.cmpnd.to.excl$Compound))
# original number of metabolites
nrow(vf.cell.neg.raw.grp.diff)
[1] 139
# number of metabolites after filtering
nrow(vf.cell.neg.cmpnd.to.incl)
[1] 132
vf.cell.pos.raw.grp.mean <- vf.cell.pos.raw %>%
group_by(Group) %>%
summarize_at(vars(matches("hVPA_FApC")), mean, na.rm = TRUE) %>%
gather(key = "Compound", value = "Grp_mean_abun", -Group)
vf.cell.pos.raw.grp.mean %>%
ggplot(aes(log2(Grp_mean_abun), color = Group)) +
geom_density(size = 2, alpha = 0.8) +
ggtitle("Distribution of compound means\nVPA + FA HILIC / Cells / Positive Mode\nGrouped by sample type")
vf.cell.pos.raw.grp.mean.order <- vf.cell.pos.raw.grp.mean %>%
filter(Group == "sample") %>%
arrange(Grp_mean_abun)
vf.cell.pos.raw %>%
select(Samples, Group, starts_with("hVPA_FApC")) %>%
gather("Compound", value = "Abundance", -c(Samples, Group)) %>%
mutate(Cmpnd_sort = factor(Compound, levels = vf.cell.pos.raw.grp.mean.order$Compound)) %>%
ggplot(aes(Cmpnd_sort, log2(Abundance), color = Group, group = Samples)) +
geom_line(alpha = 0.1, size = 1) +
theme(axis.text.x = element_blank(), axis.ticks.x = element_blank()) +
xlab("Compound") +
geom_line(
data = vf.cell.pos.raw.grp.mean %>%
mutate(Cmpnd_sort = factor(Compound, levels = vf.cell.pos.raw.grp.mean.order$Compound)),
aes(Cmpnd_sort, log2(Grp_mean_abun), color = Group, group = Group),
size = 0.5
) +
ggtitle("Profile Plot of all compound abundances\nWith average per sample type overlaid\nVPA + FA HILIC / Cells / Positive Mode")
vf.cell.pos.raw.grp.mean %>%
mutate(Cmpnd_sort = factor(Compound, levels = vf.cell.pos.raw.grp.mean.order$Compound)) %>%
ggplot(aes(Cmpnd_sort, log2(Grp_mean_abun), color = Group, group = Group)) +
geom_point(size = 1, alpha = 0.8) +
geom_line(alpha = 0.8) +
theme(axis.text.x = element_blank(), axis.ticks.x = element_blank()) +
xlab("Compound") +
ylab("log2(Sample Type Mean)") +
ggtitle("Profile Plot of compound means by sample type only\nVPA + FA HILIC / Cells / Positive Mode")
vf.cell.pos.raw.grp.diff <- vf.cell.pos.raw.grp.mean %>%
spread(Group, Grp_mean_abun) %>%
mutate(
smpl_solv_diff = sample / solv
)
vf.cell.pos.raw.grp.diff %>%
ggplot(aes(log2(smpl_solv_diff))) +
geom_histogram(bins = 50)
# include compounds with FC > 2.5 or FC is NA (indication of NA in solv)
vf.cell.pos.cmpnd.to.incl <- vf.cell.pos.raw.grp.diff %>%
filter(smpl_solv_diff > 2.5 | is.na(smpl_solv_diff))
# original number of metabolites
nrow(vf.cell.pos.raw.grp.diff)
[1] 144
# filtered number
nrow(vf.cell.pos.cmpnd.to.incl)
[1] 142
vf.med.neg.raw.grp.mean <- vf.med.neg.raw %>%
group_by(Group) %>%
summarize_at(vars(matches("hVPA_FAnM")), mean, na.rm = TRUE) %>%
gather(key = "Compound", value = "Grp_mean_abun", -Group)
vf.med.neg.raw.grp.mean %>%
ggplot(aes(log2(Grp_mean_abun), color = Group)) +
geom_density(size = 2, alpha = 0.8) +
ggtitle("Distribution of compound means\nVPA + FA / Media HILIC / Negative Mode\nGrouped by sample type")
vf.med.neg.raw.grp.mean.order <- vf.med.neg.raw.grp.mean %>%
filter(Group == "sample") %>%
arrange(Grp_mean_abun)
vf.med.neg.raw %>%
select(Samples, Group, starts_with("hVPA_FAnM")) %>%
gather("Compound", value = "Abundance", -c(Samples, Group)) %>%
mutate(Cmpnd_sort = factor(Compound, levels = vf.med.neg.raw.grp.mean.order$Compound)) %>%
ggplot(aes(Cmpnd_sort, log2(Abundance), color = Group, group = Samples)) +
geom_line(alpha = 0.1, size = 2) +
theme(axis.text.x = element_blank(), axis.ticks.x = element_blank()) +
xlab("Compound") +
geom_line(
data = vf.med.neg.raw.grp.mean %>%
mutate(Cmpnd_sort = factor(Compound, levels = vf.med.neg.raw.grp.mean.order$Compound)),
aes(Cmpnd_sort, log2(Grp_mean_abun), color = Group, group = Group),
size = 0.5
) +
ggtitle("Profile Plot of all compound abundances\nWith average per sample type overlaid\nVPA + FA HILIC / Media / Negative Mode")
vf.med.neg.raw.grp.mean %>%
mutate(Cmpnd_sort = factor(Compound, levels = vf.med.neg.raw.grp.mean.order$Compound)) %>%
ggplot(aes(Cmpnd_sort, log2(Grp_mean_abun), color = Group, group = Group)) +
geom_point(size = 1, alpha = 0.8) +
geom_line(alpha = 0.8) +
theme(axis.text.x = element_blank(), axis.ticks.x = element_blank()) +
xlab("Compound") +
ylab("log2(Sample Type Mean)") +
ggtitle("Profile Plot of compound means by sample type only\nVPA + FA HILIC / Media / Negative Mode")
vf.med.neg.raw.grp.diff <- vf.med.neg.raw.grp.mean %>%
spread(Group, Grp_mean_abun) %>%
mutate(
smpl_solv_diff = sample / solv
)
vf.med.neg.raw.grp.diff %>%
ggplot(aes(log2(smpl_solv_diff))) +
geom_histogram(bins = 25)
# include compounds with FC > 2.5 or FC is NA (indication of NA in solv)
vf.med.neg.cmpnd.to.incl <- vf.med.neg.raw.grp.diff %>%
filter(smpl_solv_diff > 2.5 | is.na(smpl_solv_diff))
nrow(vf.med.neg.raw.grp.diff)
[1] 56
nrow(vf.med.neg.cmpnd.to.incl)
[1] 52
vf.med.pos.raw.grp.mean <- vf.med.pos.raw %>%
group_by(Group) %>%
summarize_at(vars(matches("hVPA_FApM")), mean, na.rm = TRUE) %>%
gather(key = "Compound", value = "Grp_mean_abun", -Group)
vf.med.pos.raw.grp.mean %>%
ggplot(aes(log2(Grp_mean_abun), color = Group)) +
geom_density(size = 2, alpha = 0.8) +
ggtitle("Distribution of compound means\nVPA + FA HILIC / Media / Positive Mode\nGrouped by sample type")
vf.med.pos.raw.grp.mean.order <- vf.med.pos.raw.grp.mean %>%
filter(Group == "sample") %>%
arrange(Grp_mean_abun)
vf.med.pos.raw %>%
select(Samples, Group, starts_with("hVPA_FApM")) %>%
gather("Compound", value = "Abundance", -c(Samples, Group)) %>%
mutate(Cmpnd_sort = factor(Compound, levels = vf.med.pos.raw.grp.mean.order$Compound)) %>%
ggplot(aes(Cmpnd_sort, log2(Abundance), color = Group, group = Samples)) +
geom_line(alpha = 0.1, size = 2) +
theme(axis.text.x = element_blank(), axis.ticks.x = element_blank()) +
xlab("Compound") +
geom_line(
data = vf.med.pos.raw.grp.mean %>%
mutate(Cmpnd_sort = factor(Compound, levels = vf.med.pos.raw.grp.mean.order$Compound)),
aes(Cmpnd_sort, log2(Grp_mean_abun), color = Group, group = Group),
size = 0.5
) +
ggtitle("Profile Plot of all compound abundances\nWith average per sample type overlaid\nVPA + FA HILIC / Media / Positive Mode")
vf.med.pos.raw.grp.mean %>%
mutate(Cmpnd_sort = factor(Compound, levels = vf.med.pos.raw.grp.mean.order$Compound)) %>%
ggplot(aes(Cmpnd_sort, log2(Grp_mean_abun), color = Group, group = Group)) +
geom_point(size = 1, alpha = 0.8) +
geom_line(alpha = 0.8) +
theme(axis.text.x = element_blank(), axis.ticks.x = element_blank()) +
xlab("Compound") +
ylab("log2(Sample Type Mean)") +
ggtitle("Profile Plot of compound means by sample type only\nVPA + FA HILIC / Media / Positive Mode")
vf.med.pos.raw.grp.diff <- vf.med.pos.raw.grp.mean %>%
spread(Group, Grp_mean_abun) %>%
mutate(
smpl_solv_diff = sample / solv
)
vf.med.pos.raw.grp.diff %>%
ggplot(aes(log2(smpl_solv_diff))) +
geom_histogram(bins = 25)
# include compounds with FC > 2.5 or FC is NA (indication of NA in solv)
vf.med.pos.cmpnd.to.incl <- vf.med.pos.raw.grp.diff %>%
filter(smpl_solv_diff > 2.5 | is.na(smpl_solv_diff))
nrow(vf.med.pos.raw.grp.diff)
[1] 47
nrow(vf.med.pos.cmpnd.to.incl)
[1] 47
vf.cell.neg.noNA <- vf.cell.neg.raw %>%
select(Samples:Plate, one_of(vf.cell.neg.cmpnd.to.incl$Compound)) %>%
ReplaceNAwMinLogTransformMult("hVPA_FAnC")
vf.cell.pos.noNA <- vf.cell.pos.raw %>%
select(Samples:Plate, one_of(vf.cell.pos.cmpnd.to.incl$Compound)) %>%
ReplaceNAwMinLogTransformMult("hVPA_FApC")
vf.med.neg.noNA <- vf.med.neg.raw %>%
select(Samples:Plate, one_of(vf.med.neg.cmpnd.to.incl$Compound)) %>%
ReplaceNAwMinLogTransformMult("hVPA_FAnM")
vf.med.pos.noNA <- vf.med.pos.raw %>%
select(Samples:Plate, one_of(vf.med.pos.cmpnd.to.incl$Compound)) %>%
ReplaceNAwMinLogTransformMult("hVPA_FApM")
vf.cell.neg.noNA.gathered <- vf.cell.neg.noNA %>%
gather(
key = "Metabolite", "Abundance",
which(colnames(vf.cell.neg.noNA) == "hVPA_FAnC10"):ncol(vf.cell.neg.noNA)
)
# plot all abundances in a sample, grouped by sample as a boxplot
vf.cell.neg.noNA.gathered %>%
ggplot(aes(Samples, Abundance, fill = Group)) +
geom_boxplot() +
geom_boxplot(aes(color = Group), fatten = NULL, fill = NA, coef = 0, outlier.alpha = 0, show.legend = FALSE) +
theme(axis.text.x = element_text(angle = 90)) +
ylab("log2(Abundance)") +
ggtitle("Boxplot of compound abundances\nAll samples\nVPA + FA HILIC / Cells / Negative Mode")
# same data format, but as ridge plots
vf.cell.neg.noNA.gathered %>%
ggplot(aes(y = Samples, x = Abundance, fill = Group)) +
geom_density_ridges(scale = 15) +
theme_ridges() +
scale_y_discrete(expand = c(0.01, 0)) +
ggtitle("Ridge plot of compound abundances\nAll samples\nVPA + FA HILIC/ Cells / Negative Mode")
Picking joint bandwidth of 0.972
# experimental samples only
vf.cell.neg.noNA.gathered %>%
filter(Group == "sample") %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(y = Samples, x = Abundance, fill = Treatment)) +
geom_density_ridges(scale = 10) +
theme_ridges() +
scale_y_discrete(expand = c(0.01, 0)) +
ggtitle("Ridge plot of compound abundances\nExperimental samples only\nVPA + FA HILIC / Cells / Negative Mode")
Picking joint bandwidth of 0.93
# overlay the distributions for another look
vf.cell.neg.noNA.gathered %>%
filter(Group == "sample") %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(Abundance, group = Samples, color = Treatment)) +
geom_density(alpha = 0.8, size = 0.75) +
xlab("log2(Abundance)") +
ggtitle("Density plot of compound abundances\nExperimental samples only\nVPA + FA HILIC / Cells / Negative Mode")
vf.cell.pos.noNA.gathered <- vf.cell.pos.noNA %>%
gather(
key = "Metabolite", "Abundance",
which(colnames(vf.cell.pos.noNA) == "hVPA_FApC1"):ncol(vf.cell.pos.noNA)
)
vf.cell.pos.noNA.gathered %>%
ggplot(aes(Samples, Abundance, fill = Group)) +
geom_boxplot() +
geom_boxplot(aes(color = Group), fatten = NULL, fill = NA, coef = 0, outlier.alpha = 0, show.legend = FALSE) +
theme(axis.text.x = element_text(angle = 90)) +
ylab("log2(Abundance)") +
ggtitle("Boxplot of compound abundances\nAll samples\nVPA + FA HILIC / Cells / Positive Mode")
vf.cell.pos.noNA.gathered %>%
ggplot(aes(y = Samples, x = Abundance, fill = Group)) +
geom_density_ridges(scale = 15) +
theme_ridges() +
scale_y_discrete(expand = c(0.01, 0)) +
ggtitle("Ridge plot of compound abundances\nAll samples\nVPA + FA HILIC / Cells / Positive Mode")
Picking joint bandwidth of 1.19
vf.cell.pos.noNA.gathered %>%
filter(Group == "sample") %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(y = Samples, x = Abundance, fill = Treatment)) +
geom_density_ridges(scale = 10) +
theme_ridges() +
scale_y_discrete(expand = c(0.01, 0)) +
ggtitle("Ridge plot of compound abundances\nExperimental samples only\nVPA + FA HILIC / Cells / Positive Mode")
Picking joint bandwidth of 1.18
vf.cell.pos.noNA.gathered %>%
filter(Group == "sample") %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(Abundance, group = Samples, color = Treatment)) +
geom_density(alpha = 0.8, size = 0.75) +
xlab("log2(Abundance)") +
ggtitle("Density plot of compound abundances\nExperimental samples only\nVPA + FA HILIC / Cells / Positive Mode")
vf.med.neg.noNA.gathered <- vf.med.neg.noNA %>%
gather(
key = "Metabolite", "Abundance",
which(colnames(vf.med.neg.noNA) == "hVPA_FAnM10"):ncol(vf.med.neg.noNA)
)
vf.med.neg.noNA.gathered %>%
ggplot(aes(Samples, Abundance, fill = Group)) +
geom_boxplot() +
geom_boxplot(aes(color = Group), fatten = NULL, fill = NA, coef = 0, outlier.alpha = 0, show.legend = FALSE) +
theme(axis.text.x = element_text(angle = 90)) +
ylab("log2(Abundance)") +
ggtitle("Boxplot of compound abundances\nAll samples\nVPA + FA HILIC / Media / Negative Mode")
vf.med.neg.noNA.gathered %>%
ggplot(aes(y = Samples, x = Abundance, fill = Group)) +
geom_density_ridges(scale = 15) +
theme_ridges() +
scale_y_discrete(expand = c(0.01, 0)) +
ggtitle("Ridge plot of compound abundances\nAll samples\nVPA + FA HILIC / Media / Negative Mode")
Picking joint bandwidth of 0.885
vf.med.neg.noNA.gathered %>%
filter(Group == "sample") %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(y = Samples, x = Abundance, fill = Treatment)) +
geom_density_ridges(scale = 10) +
theme_ridges() +
scale_y_discrete(expand = c(0.01, 0)) +
ggtitle("Ridge plot of compound abundances\nExperimental samples only\nVPA + FA HILIC / Media / Negative Mode")
Picking joint bandwidth of 0.883
vf.med.neg.noNA.gathered %>%
filter(Group == "sample") %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(Abundance, group = Samples, color = Treatment)) +
geom_density(alpha = 0.8, size = 0.75) +
xlab("log2(Abundance)") +
ggtitle("Density plot of compound abundances\nExperimental samples only\nVPA + FA HILIC / Media / Negative Mode")
vf.med.pos.noNA.gathered <- vf.med.pos.noNA %>%
gather(
key = "Metabolite", "Abundance",
which(colnames(vf.med.pos.noNA) == "hVPA_FApM1"):ncol(vf.med.pos.noNA)
)
vf.med.pos.noNA.gathered %>%
ggplot(aes(Samples, Abundance, fill = Group)) +
geom_boxplot() +
geom_boxplot(aes(color = Group), fatten = NULL, fill = NA, coef = 0, outlier.alpha = 0, show.legend = FALSE) +
theme(axis.text.x = element_text(angle = 90)) +
ylab("log2(Abundance)") +
ggtitle("Boxplot of compound abundances\nAll samples\nVPA + FA HILIC / Media / Positive Mode")
vf.med.pos.noNA.gathered %>%
ggplot(aes(y = Samples, x = Abundance, fill = Group)) +
geom_density_ridges(scale = 15) +
theme_ridges() +
scale_y_discrete(expand = c(0.01, 0)) +
ggtitle("Ridge plot of compound abundances\nAll samples\nVPA + FA HILIC / Media / Positive Mode")
Picking joint bandwidth of 1.18
vf.med.pos.noNA.gathered %>%
filter(Group == "sample") %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(y = Samples, x = Abundance, fill = Treatment)) +
geom_density_ridges(scale = 10) +
theme_ridges() +
scale_y_discrete(expand = c(0.01, 0)) +
ggtitle("Ridge plot of compound abundances\nExperimental samples only\nVPA + FA HILIC / Media / Positive Mode")
Picking joint bandwidth of 1.18
vf.med.pos.noNA.gathered %>%
filter(Group == "sample") %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(Abundance, group = Samples, color = Treatment)) +
geom_density(alpha = 0.8, size = 0.75) +
xlab("log2(Abundance)") +
ggtitle("Density plot of compound abundances\nExperimental samples only\nVPA + FA HILIC / Media / Positive Mode")
Some plots to understand the relationship between the samples, QC samples, solvent, and empty samples in some cases.
### PCA on all Samples ###
vf.cell.neg.full.pca <- vf.cell.neg.noNA %>%
select(starts_with("hVPA_FAnC")) %>%
mutate_all(scale, center = TRUE, scale = FALSE) %>%
as.matrix() %>%
prcomp()
plot(
(vf.cell.neg.full.pca$sdev ^ 2) * 100 / sum(vf.cell.neg.full.pca$sdev ^ 2),
xlab = "Principal Component",
ylab = "Variance Explained",
main = "Percent variance explained by each principal component\nAll samples only\nVPA + FA HILIC / Cells / Negative Mode",
type = "b"
)
vf.cell.neg.full.pca.x <- as.data.frame(vf.cell.neg.full.pca$x)
row.names(vf.cell.neg.full.pca.x) <- vf.cell.neg.noNA$Samples
vf.cell.neg.full.pca.x <- vf.cell.neg.full.pca.x %>%
bind_cols(vf.cell.neg.noNA %>% select(Group:Plate))
vf.cell.neg.full.pca.x %>%
ggplot(aes(x = PC1, y = PC2, color = Group)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC1 (96.4% Var)") +
ylab("PC2 (14.5% Var)") +
ggtitle("Principal Component Analysis\nAll Samples\nVPA + FA HILIC / Cells / Negative Mode")
### Samples and mix ###
vf.cell.neg.smpl.mix.pca <- vf.cell.neg.noNA %>%
filter(Group == "sample" | Group == "mix") %>%
select(starts_with("hVPA_FAnC")) %>%
mutate_all(scale, center = TRUE, scale = FALSE) %>%
as.matrix() %>%
prcomp()
plot(
(vf.cell.neg.smpl.mix.pca$sdev ^ 2) * 100 / sum(vf.cell.neg.smpl.mix.pca$sdev ^ 2),
xlab = "Principal Component",
ylab = "Variance Explained",
main = "Percent variance explained by each principal component\nSamples and Mix\nVPA + FA HILIC / Cells / Negative Mode",
type = "b"
)
vf.cell.neg.smpl.mix.pca.x <- as.data.frame(vf.cell.neg.smpl.mix.pca$x)
vf.cell.neg.smpl.mix.pca.x <- vf.cell.neg.smpl.mix.pca.x %>%
bind_cols(
vf.cell.neg.noNA %>%
filter(Group == "sample" | Group == "mix") %>%
select(Samples, Group:Plate)
)
row.names(vf.cell.neg.smpl.mix.pca.x) <- vf.cell.neg.smpl.mix.pca.x$Samples
vf.cell.neg.smpl.mix.pca.x %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(x = PC1, y = PC2, color = Treatment)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC1 (63.1% Var)") +
ylab("PC2 (14.0% Var)") +
ggtitle("Principal Component Analysis\nSamples and Mix\nVPA + FA HILIC / Cells / Negative Mode")
vf.cell.neg.smpl.mix.pca.x %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(x = PC3, y = PC4, color = Treatment)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC3 (6.2% Var)") +
ylab("PC4 (4.7% Var)") +
ggtitle("Principal Component Analysis\nSamples and mix\nVPA + FA HILIC / Cells / Negative Mode")
### Experimental Samples Only ###
vf.cell.neg.smpl.pca <- vf.cell.neg.noNA %>%
filter(Group == "sample") %>%
select(starts_with("hVPA_FAnC")) %>%
mutate_all(scale, center = TRUE, scale = FALSE) %>%
as.matrix() %>%
prcomp()
plot(
(vf.cell.neg.smpl.pca$sdev ^ 2) * 100 / sum(vf.cell.neg.smpl.pca$sdev ^ 2),
xlab = "Principal Component",
ylab = "Variance Explained",
main = "Percent variance explained by each principal component\nExperimental samples only\nVPA + FA HILIC / Cells / Negative Mode",
type = "b"
)
vf.cell.neg.smpl.pca.x <- as.data.frame(vf.cell.neg.smpl.pca$x)
vf.cell.neg.smpl.pca.x <- vf.cell.neg.smpl.pca.x %>%
bind_cols(
vf.cell.neg.noNA %>%
filter(Group == "sample") %>%
select(Samples, Group:Plate)
)
row.names(vf.cell.neg.smpl.pca.x) <- vf.cell.neg.smpl.pca.x$Samples
vf.cell.neg.smpl.pca.x %>%
ggplot(aes(x = PC1, y = PC2, color = VPA, shape = FA)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC1 (65.3% Var)") +
ylab("PC2 (14.6% Var)") +
ggtitle("Principal Component Analysis\nExperimental samples only\nVPA + FA HILIC / Cells / Negative Mode")
vf.cell.neg.smpl.pca.x %>%
ggplot(aes(x = PC3, y = PC4, color = VPA, shape = FA)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC3 (5.7% Var)") +
ylab("PC4 (4.2% Var)") +
ggtitle("Principal Component Analysis\nExperimental samples only\nVPA + FA HILIC/ Cells / Negative Mode")
vf.cell.pos.full.pca <- vf.cell.pos.noNA %>%
select(starts_with("hVPA_FApC")) %>%
mutate_all(scale, center = TRUE, scale = FALSE) %>%
as.matrix() %>%
prcomp()
plot(
(vf.cell.pos.full.pca$sdev ^ 2) * 100 / sum(vf.cell.pos.full.pca$sdev ^ 2),
xlab = "Principal Component",
ylab = "Variance Explained",
main = "Percent variance explained by each principal component\nAll samples only\nVPA + FA HILIC / Cells / Positive Mode",
type = "b"
)
vf.cell.pos.full.pca.x <- as.data.frame(vf.cell.pos.full.pca$x)
row.names(vf.cell.pos.full.pca.x) <- vf.cell.pos.noNA$Samples
vf.cell.pos.full.pca.x <- vf.cell.pos.full.pca.x %>%
bind_cols(vf.cell.pos.noNA %>% select(Group:Plate))
vf.cell.pos.full.pca.x %>%
ggplot(aes(x = PC1, y = PC2, color = Group)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC1 (92.4% Var)") +
ylab("PC2 (2.7% Var)") +
ggtitle("Principal Component Analysis\nAll Samples\nVPA + FA HILIC / Cells / Positive Mode")
### Samples and Mix ###
vf.cell.pos.smpl.mix.pca <- vf.cell.pos.noNA %>%
filter(Group == "sample" | Group == "mix") %>%
select(starts_with("hVPA_FApC")) %>%
mutate_all(scale, center = TRUE, scale = FALSE) %>%
as.matrix() %>%
prcomp()
plot(
(vf.cell.pos.smpl.mix.pca$sdev ^ 2) * 100 / sum(vf.cell.pos.smpl.mix.pca$sdev ^ 2),
xlab = "Principal Component",
ylab = "Variance Explained",
main = "Percent variance explained by each principal component\nSamples and Mix\nVPA + FA HILIC / Cells / Positive Mode",
type = "b"
)
vf.cell.pos.smpl.mix.pca.x <- as.data.frame(vf.cell.pos.smpl.mix.pca$x)
vf.cell.pos.smpl.mix.pca.x <- vf.cell.pos.smpl.mix.pca.x %>%
bind_cols(
vf.cell.pos.noNA %>%
filter(Group == "sample" | Group == "mix") %>%
select(Samples, Group:Plate)
)
row.names(vf.cell.pos.smpl.mix.pca.x) <- vf.cell.pos.smpl.mix.pca.x$Samples
vf.cell.pos.smpl.mix.pca.x %>%
unite("Treatment", VPA:FA, sep = "_", remove = FALSE) %>%
ggplot(aes(x = PC1, y = PC2, color = Treatment, shape = VPA)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC1 (62.9% Var)") +
ylab("PC2 (13.6% Var)") +
ggtitle("Principal Component Analysis\nSamples and Mix\nVPA + FA / Cells / Positive Mode")
vf.cell.pos.smpl.mix.pca.x %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(x = PC3, y = PC4, color = Treatment)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC3 (7.2% Var)") +
ylab("PC4 (3.8% Var)") +
ggtitle("Principal Component Analysis\nSamples and Mix\nVPA + FA HILIC / Cells / Positive Mode")
### Experimental Samples Only ###
vf.cell.pos.smpl.pca <- vf.cell.pos.noNA %>%
filter(Group == "sample") %>%
select(starts_with("hVPA_FApC")) %>%
mutate_all(scale, center = TRUE, scale = FALSE) %>%
as.matrix() %>%
prcomp()
plot(
(vf.cell.pos.smpl.pca$sdev ^ 2) * 100 / sum(vf.cell.pos.smpl.pca$sdev ^ 2),
xlab = "Principal Component",
ylab = "Variance Explained",
main = "Percent variance explained by each principal component\nExperimental samples only\nVPA + FA HILIC/ Cells / Positive Mode",
type = "b"
)
vf.cell.pos.smpl.pca.x <- as.data.frame(vf.cell.pos.smpl.pca$x)
vf.cell.pos.smpl.pca.x <- vf.cell.pos.smpl.pca.x %>%
bind_cols(
vf.cell.pos.noNA %>%
filter(Group == "sample") %>%
select(Samples, Group:Plate)
)
row.names(vf.cell.pos.smpl.pca.x) <- vf.cell.pos.smpl.pca.x$Samples
vf.cell.pos.smpl.pca.x %>%
ggplot(aes(x = PC1, y = PC2, color = FA, shape = VPA)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC1 (61.2% Var)") +
ylab("PC2 (15.2% Var)") +
ggtitle("Principal Component Analysis\nExperimental samples only\nVPA + FA HILIC / Cells / Positive Mode")
vf.cell.pos.smpl.pca.x %>%
ggplot(aes(x = PC3, y = PC4, color = FA, shape = VPA)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC3 (7.7% Var)") +
ylab("PC4 (4.3% Var)") +
ggtitle("Principal Component Analysis\nExperimental samples only\nVPA + FA HILIC / Cells / Positive Mode")
### PCA on all Samples ###
vf.med.neg.full.pca <- vf.med.neg.noNA %>%
select(starts_with("hVPA_FAnM")) %>%
mutate_all(scale, center = TRUE, scale = FALSE) %>%
as.matrix() %>%
prcomp()
plot(
(vf.med.neg.full.pca$sdev ^ 2) * 100 / sum(vf.med.neg.full.pca$sdev ^ 2),
xlab = "Principal Component",
ylab = "Variance Explained",
main = "Percent variance explained by each principal component\nAll samples only\nVPA + FA / Media / Negative Mode",
type = "b"
)
vf.med.neg.full.pca.x <- as.data.frame(vf.med.neg.full.pca$x)
row.names(vf.med.neg.full.pca.x) <- vf.med.neg.noNA$Samples
vf.med.neg.full.pca.x <- vf.med.neg.full.pca.x %>%
bind_cols(vf.med.neg.noNA %>% select(Group:Plate))
vf.med.neg.full.pca.x %>%
ggplot(aes(x = PC1, y = PC2, color = Group)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC1 (89.8% Var)") +
ylab("PC2 (4.7% Var)") +
ggtitle("Principal Component Analysis\nAll Samples\nVPA + FA / Media / Negative Mode")
### Samples and Mix ###
vf.med.neg.smpl.mix.pca <- vf.med.neg.noNA %>%
filter(Group == "sample" | Group == "mix") %>%
select(starts_with("hVPA_FAnM")) %>%
mutate_all(scale, center = TRUE, scale = FALSE) %>%
as.matrix() %>%
prcomp()
plot(
(vf.med.neg.smpl.mix.pca$sdev ^ 2) * 100 / sum(vf.med.neg.smpl.mix.pca$sdev ^ 2),
xlab = "Principal Component",
ylab = "Variance Explained",
main = "Percent variance explained by each principal component\nSamples and Mix\nVPA + FA / Media / Negative Mode",
type = "b"
)
vf.med.neg.smpl.mix.pca.x <- as.data.frame(vf.med.neg.smpl.mix.pca$x)
vf.med.neg.smpl.mix.pca.x <- vf.med.neg.smpl.mix.pca.x %>%
bind_cols(
vf.med.neg.noNA %>%
filter(Group == "sample" | Group == "mix") %>%
select(Samples, Group:Plate)
)
row.names(vf.med.neg.smpl.mix.pca.x) <- vf.med.neg.smpl.mix.pca.x$Samples
vf.med.neg.smpl.mix.pca.x %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(x = PC1, y = PC2, color = Treatment)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC1 (67.1% Var)") +
ylab("PC2 (19.6% Var)") +
ggtitle("Principal Component Analysis\nSamples and Mix\nVPA + FA / Media / Negative Mode")
vf.med.neg.smpl.mix.pca.x %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(x = PC3, y = PC4, color = Treatment)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC3 (4.3% Var)") +
ylab("PC4 (2.1% Var)") +
ggtitle("Principal Component Analysis\nSamples and Mix\nVPA + FA / Media / Negative Mode")
### Experimental Samples Only ###
vf.med.neg.smpl.pca <- vf.med.neg.noNA %>%
filter(Group == "sample") %>%
select(starts_with("hVPA_FAnM")) %>%
mutate_all(scale, center = TRUE, scale = FALSE) %>%
as.matrix() %>%
prcomp()
plot(
(vf.med.neg.smpl.pca$sdev ^ 2) * 100 / sum(vf.med.neg.smpl.pca$sdev ^ 2),
xlab = "Principal Component",
ylab = "Variance Explained",
main = "Percent variance explained by each principal component\nExperimental samples only\nVPA + FA / Media / Negative Mode",
type = "b"
)
vf.med.neg.smpl.pca.x <- as.data.frame(vf.med.neg.smpl.pca$x)
vf.med.neg.smpl.pca.x <- vf.med.neg.smpl.pca.x %>%
bind_cols(
vf.med.neg.noNA %>%
filter(Group == "sample") %>%
select(Samples, Group:Plate)
)
row.names(vf.med.neg.smpl.pca.x) <- vf.med.neg.smpl.pca.x$Samples
vf.med.neg.smpl.pca.x %>%
ggplot(aes(x = PC1, y = PC2, color = FA, shape = VPA)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC1 (74.4% Var)") +
ylab("PC2 (12.1% Var)") +
ggtitle("Principal Component Analysis\nExperimental samples only\nVPA + FA / Media / Negative Mode")
vf.med.neg.smpl.pca.x %>%
ggplot(aes(x = PC3, y = PC4, color = FA, shape = VPA)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC3 (4.5% Var)") +
ylab("PC4 (2.2% Var)") +
ggtitle("Principal Component Analysis\nExperimental samples only\nVPA + FA / Media / Negative Mode")
### PCA on all Samples ###
vf.med.pos.full.pca <- vf.med.pos.noNA %>%
select(starts_with("hVPA_FApM")) %>%
mutate_all(scale, center = TRUE, scale = FALSE) %>%
as.matrix() %>%
prcomp()
plot(
(vf.med.pos.full.pca$sdev ^ 2) * 100 / sum(vf.med.pos.full.pca$sdev ^ 2),
xlab = "Principal Component",
ylab = "Variance Explained",
main = "Percent variance explained by each principal component\nAll samples only\nVPA + FA / Media / Positive Mode",
type = "b"
)
vf.med.pos.full.pca.x <- as.data.frame(vf.med.pos.full.pca$x)
row.names(vf.med.pos.full.pca.x) <- vf.med.pos.noNA$Samples
vf.med.pos.full.pca.x <- vf.med.pos.full.pca.x %>%
bind_cols(vf.med.pos.noNA %>% select(Group:Plate))
vf.med.pos.full.pca.x %>%
ggplot(aes(x = PC1, y = PC2, color = Group)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC1 (88.6% Var)") +
ylab("PC2 (4.7% Var)") +
ggtitle("Principal Component Analysis\nAll Samples\nVPA + FA / Media / Positive Mode")
### Samples and mix ###
vf.med.pos.smpl.mix.pca <- vf.med.pos.noNA %>%
filter(Group == "sample" | Group == "mix") %>%
select(starts_with("hVPA_FApM")) %>%
mutate_all(scale, center = TRUE, scale = FALSE) %>%
as.matrix() %>%
prcomp()
plot(
(vf.med.pos.smpl.mix.pca$sdev ^ 2) * 100 / sum(vf.med.pos.smpl.mix.pca$sdev ^ 2),
xlab = "Principal Component",
ylab = "Variance Explained",
main = "Percent variance explained by each principal component\nSamples and Mix\nVPA + FA / Media / Positive Mode",
type = "b"
)
vf.med.pos.smpl.mix.pca.x <- as.data.frame(vf.med.pos.smpl.mix.pca$x)
vf.med.pos.smpl.mix.pca.x <- vf.med.pos.smpl.mix.pca.x %>%
bind_cols(
vf.med.pos.noNA %>%
filter(Group == "sample" | Group == "mix") %>%
select(Samples, Group:Plate)
)
row.names(vf.med.pos.smpl.mix.pca.x) <- vf.med.pos.smpl.mix.pca.x$Samples
vf.med.pos.smpl.mix.pca.x %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(x = PC1, y = PC2, color = Treatment)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC1 (53.7% Var)") +
ylab("PC2 (18.9% Var)") +
ggtitle("Principal Component Analysis\nSamples and Mix\nVPA + FA / Media / Positive Mode")
vf.med.pos.smpl.mix.pca.x %>%
unite("Treatment", VPA:FA, sep = "_") %>%
ggplot(aes(x = PC3, y = PC4, color = Treatment)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC3 (8.7% Var)") +
ylab("PC4 (6.0% Var)") +
ggtitle("Principal Component Analysis\nSamples and Mix\nVPA + FA / Media / Positive Mode")
### Experimental Samples Only ###
vf.med.pos.smpl.pca <- vf.med.pos.noNA %>%
filter(Group == "sample") %>%
select(starts_with("hVPA_FApM")) %>%
mutate_all(scale, center = TRUE, scale = FALSE) %>%
as.matrix() %>%
prcomp()
plot(
(vf.med.pos.smpl.pca$sdev ^ 2) * 100 / sum(vf.med.pos.smpl.pca$sdev ^ 2),
xlab = "Principal Component",
ylab = "Variance Explained",
main = "Percent variance explained by each principal component\nExperimental samples only\nVPA + FA / Media / Positive Mode",
type = "b"
)
vf.med.pos.smpl.pca.x <- as.data.frame(vf.med.pos.smpl.pca$x)
vf.med.pos.smpl.pca.x <- vf.med.pos.smpl.pca.x %>%
bind_cols(
vf.med.pos.noNA %>%
filter(Group == "sample") %>%
select(Samples, Group:Plate)
)
row.names(vf.med.pos.smpl.pca.x) <- vf.med.pos.smpl.pca.x$Samples
vf.med.pos.smpl.pca.x %>%
ggplot(aes(x = PC1, y = PC2, color = FA, shape = VPA)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC1 (53.8% Var)") +
ylab("PC2 (19.8% Var)") +
ggtitle("Principal Component Analysis\nExperimental samples only\nVPA + FA / Media / Positive Mode")
vf.med.pos.smpl.pca.x %>%
ggplot(aes(x = PC3, y = PC4, color = FA, shape = VPA)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC3 (8.8% Var)") +
ylab("PC4 (5.8% Var)") +
ggtitle("Principal Component Analysis\nExperimental samples only\nVPA + FA / Media / Positive Mode")
# sample prep
vf.cell.neg.smpl.data <- vf.cell.neg.noNA %>%
filter(Group == "sample") %>%
unite("Treatment", VPA:FA, sep = "_")
vf.cell.neg.data.for.sva <- as.matrix(
vf.cell.neg.smpl.data[, which(
colnames(vf.cell.neg.smpl.data) == "hVPA_FAnC10"
):ncol(vf.cell.neg.smpl.data)]
)
row.names(vf.cell.neg.data.for.sva) <- vf.cell.neg.smpl.data$Samples
vf.cell.neg.data.for.sva <- t(vf.cell.neg.data.for.sva)
# pheno prep
vf.cell.neg.data.pheno <- as.data.frame(vf.cell.neg.smpl.data[, 5:6])
row.names(vf.cell.neg.data.pheno) <- vf.cell.neg.smpl.data$Samples
# sva calculation
vf.cell.neg.mod.vf <- model.matrix(~ 0 + as.factor(Treatment), data = vf.cell.neg.data.pheno)
vf.cell.neg.mod0 <- model.matrix(~ 1, data = vf.cell.neg.data.pheno)
set.seed(2018)
num.sv(vf.cell.neg.data.for.sva, vf.cell.neg.mod.vf, method = "be")
[1] 1
set.seed(2018)
num.sv(vf.cell.neg.data.for.sva, vf.cell.neg.mod.vf, method = "leek")
[1] 1
set.seed(2018)
vf.cell.neg.sv <- sva(vf.cell.neg.data.for.sva, vf.cell.neg.mod.vf, vf.cell.neg.mod0)
Number of significant surrogate variables is: 1
Iteration (out of 5 ):1 2 3 4 5
# extract the surrogate variables
vf.cell.neg.surr.var <- as.data.frame(vf.cell.neg.sv$sv)
colnames(vf.cell.neg.surr.var) <- c("S1")
colnames(vf.cell.neg.mod.vf) <- c("cntrl", "fa_only", "vpa_only", "fa_and_vpa")
# combine the full model matrix and the surrogate variables into one
vf.cell.neg.design.sv <- cbind(vf.cell.neg.mod.vf, vf.cell.neg.surr.var)
vf.cell.neg.cont.mat <- makeContrasts(
vpa_lowFA = vpa_only - cntrl,
vpa_highFA = fa_and_vpa - fa_only,
FA_diff = (fa_and_vpa - fa_only) - (vpa_only - cntrl),
levels = c("cntrl", "fa_only", "vpa_only", "fa_and_vpa", "S1")
)
# fit the model/design matrix
vf.cell.neg.eb <- vf.cell.neg.data.for.sva %>%
lmFit(vf.cell.neg.design.sv) %>%
contrasts.fit(vf.cell.neg.cont.mat) %>%
eBayes()
# pull out the results for each metabolite for each comparison
vf.cell.neg.eb.tidy <- tidy(vf.cell.neg.eb) %>%
mutate(
adj_pval = p.adjust(p.value, method = "bonferroni"),
FC = 2 ^ estimate,
change_in_vpa = ifelse(FC < 1, "down", "up")
) %>%
rename(compound_short = gene)
# volcano plot
vf.cell.neg.eb.tidy %>%
ggplot(aes(estimate, -log10(adj_pval))) +
geom_point(size = 2, alpha = 0.5) +
geom_hline(linetype = "dashed", color = "#009E73", yintercept = -log10(0.05)) +
geom_vline(linetype = "dashed", color = "#CC79A7", xintercept = log2(1.2)) +
geom_vline(linetype = "dashed", color = "#CC79A7", xintercept = log2(1/1.2)) +
xlim(-2.5, 2.5) +
xlab("log2(FC)") +
ylab("-log10(adjusted p-value)") +
ggtitle("Volcano plot\nVPA + FA HILIC / Cells / Negative Mode")
# select statistically significant hits with a certain FC:
vf.cell.neg.hits <- vf.cell.neg.eb.tidy %>%
filter(adj_pval < 0.05 & (FC > 1.2 | FC < 1/1.2)) %>%
inner_join(vf.cell.neg.compound.info, by = "compound_short")
# how many metabolites are significant across the different contrats
table(vf.cell.neg.hits$term)
FA_diff vpa_highFA vpa_lowFA
0 13 14
# significant metabolites
sort(unique(vf.cell.neg.hits$compound_full))
[1] "3-Sulfinoalanine"
[2] "3,4-Dihydroxyphenylacetic Acid (DOPAC)"
[3] "ATP"
[4] "BAIBA"
[5] "Caprylic Acid"
[6] "Creatinine"
[7] "Cystathionine"
[8] "D-Galactitol"
[9] "D-Glucose 6-phosphate"
[10] "D-Sorbitol"
[11] "Docosahexaenoic Acid (22:6 n-3)"
[12] "GABA"
[13] "Glutamic Acid"
[14] "GSSG"
[15] "myo-Inositol"
[16] "N-Acetylglutamic Acid"
[17] "N-Acetylserine"
[18] "Oleic Acid"
[19] "Palmitoleic Acid"
[20] "Proline"
[21] "Tryptophan"
[22] "UDP-N-Acetylgalactosamine"
[23] "UTP"
vf.cell.neg.hits.tally2 <- vf.cell.neg.hits %>%
group_by(compound_short, compound_full) %>%
count() %>%
filter(n == 2)
vf.cell.neg.lowFA.hits <- vf.cell.neg.hits %>%
filter(term == "vpa_lowFA" & !(compound_short %in% vf.cell.neg.hits.tally2$compound_short))
vf.cell.neg.highFA.hits <- vf.cell.neg.hits %>%
filter(term == "vpa_highFA" & !(compound_short %in% vf.cell.neg.hits.tally2$compound_short))
vf.cell.neg.both.hits <- vf.cell.neg.hits %>%
filter(compound_short %in% vf.cell.neg.hits.tally2$compound_short) %>%
arrange(compound_short, term)
vf.cell.neg.both.hits %>%
select(compound_full, term, FC) %>%
spread(key = "term", value = "FC") %>%
ggplot(aes(vpa_lowFA, vpa_highFA)) +
geom_point(size = 2, alpha = 0.8) +
geom_abline(intercept = 0, slope = 1, color = "blue", alpha = 0.8)
vf.cell.neg.both.hits %>%
select(compound_full, term, FC) %>%
spread(key = "term", value = "FC") %>%
mutate(diff = vpa_highFA - vpa_lowFA) %>%
arrange(diff)
# A tibble: 4 x 4
compound_full vpa_highFA vpa_lowFA diff
<chr> <dbl> <dbl> <dbl>
1 Docosahexaenoic Acid (22:6 n-3) 1.86 2.94 -1.08
2 D-Sorbitol 0.456 0.374 0.0824
3 Cystathionine 2.25 2.00 0.253
4 Proline 3.00 2.66 0.338
### Plotting ###
vf.cell.neg.gathered <- vf.cell.neg.noNA %>%
filter(Group == "sample") %>%
bind_cols(vf.cell.neg.surr.var) %>%
select(Samples, VPA, FA, S1, starts_with("hVPA_FAnC")) %>%
gather(key = "Compound", value = "Abundance", hVPA_FAnC10:hVPA_FAnC99)
vf.cell.neg.nested <- vf.cell.neg.gathered %>%
group_by(Compound) %>%
nest() %>%
mutate(model = map(data, ~lm(Abundance ~ S1, data = .))) %>%
mutate(augment_model = map(model, augment))
vf.cell.neg.modSV.resid <- vf.cell.neg.nested %>%
unnest(data, augment_model) %>%
select(Samples, VPA, FA, Compound, .resid) %>%
spread(Compound, .resid)
vf.cell.neg.modSV.resid %>%
select(Samples:FA, one_of(unique(vf.cell.neg.hits$compound_short))) %>%
HeatmapPrepAlt("hVPA_FAnC") %>%
t() %>%
heatmaply(
colors = viridis(n = 10, option = "magma"),
xlab = "Samples", ylab = "Compounds",
main = "Statistically significant compounds\nVPA + FA HILIC / Cells / Neg Mode",
margins = c(50, 50, 75, 30),
k_col = 2, k_row = 2,
labRow = unique(vf.cell.neg.hits$compound_full)
)
### PCA - cleaned data ###
vf.cell.neg.modSV.pca <- vf.cell.neg.modSV.resid %>%
select(starts_with("hVPA_FAnC")) %>%
mutate_all(scale, center = TRUE, scale = FALSE) %>%
as.matrix() %>%
prcomp()
vf.cell.neg.modSV.pca.x <- as.data.frame(vf.cell.neg.modSV.pca$x)
row.names(vf.cell.neg.modSV.pca.x) <- vf.cell.neg.modSV.resid$Samples
vf.cell.neg.modSV.pca.x <- vf.cell.neg.modSV.pca.x %>%
bind_cols(vf.cell.neg.modSV.resid %>% select(VPA:FA))
vf.cell.neg.modSV.pca.x %>%
ggplot(aes(x = PC1, y = PC2, color = VPA, shape = FA)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC1 (35.3% Var)") +
ylab("PC2 (26.4% Var)")
vf.cell.neg.modSV.pca.x %>%
ggplot(aes(x = PC3, y = PC4, color = VPA, shape = FA)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC3 (11.6% Var)") +
ylab("PC4 (5.7% Var)")
vf.cell.pos.smpl.data <- vf.cell.pos.noNA %>%
filter(Group == "sample") %>%
unite("Treatment", VPA:FA, sep = "_")
vf.cell.pos.data.for.sva <- as.matrix(
vf.cell.pos.smpl.data[, which(
colnames(vf.cell.pos.smpl.data) == "hVPA_FApC1"
):ncol(vf.cell.pos.smpl.data)]
)
row.names(vf.cell.pos.data.for.sva) <- vf.cell.pos.smpl.data$Samples
vf.cell.pos.data.for.sva <- t(vf.cell.pos.data.for.sva)
vf.cell.pos.data.pheno <- as.data.frame(vf.cell.pos.smpl.data[, 5:6])
row.names(vf.cell.pos.data.pheno) <- vf.cell.pos.smpl.data$Samples
vf.cell.pos.mod.vf <- model.matrix(~ 0 + as.factor(Treatment), data = vf.cell.pos.data.pheno)
vf.cell.pos.mod0 <- model.matrix(~ 1, data = vf.cell.pos.data.pheno)
set.seed(2018)
num.sv(vf.cell.pos.data.for.sva, vf.cell.pos.mod.vf, method = "be")
[1] 1
set.seed(2018)
num.sv(vf.cell.pos.data.for.sva, vf.cell.pos.mod.vf, method = "leek")
[1] 0
set.seed(2018)
vf.cell.pos.sv <- sva(vf.cell.pos.data.for.sva, vf.cell.pos.mod.vf, vf.cell.pos.mod0)
Number of significant surrogate variables is: 1
Iteration (out of 5 ):1 2 3 4 5
vf.cell.pos.surr.var <- as.data.frame(vf.cell.pos.sv$sv)
colnames(vf.cell.pos.surr.var) <- c("S1")
colnames(vf.cell.pos.mod.vf) <- c("cntrl", "fa_only", "vpa_only", "fa_and_vpa")
vf.cell.pos.design.sv <- cbind(vf.cell.pos.mod.vf, vf.cell.pos.surr.var)
vf.cell.pos.cont.mat <- makeContrasts(
vpa_lowFA = vpa_only - cntrl,
vpa_highFA = fa_and_vpa - fa_only,
FA_diff = (fa_and_vpa - fa_only) - (vpa_only - cntrl),
levels = c("cntrl", "fa_only", "vpa_only", "fa_and_vpa", "S1")
)
vf.cell.pos.eb <- vf.cell.pos.data.for.sva %>%
lmFit(vf.cell.pos.design.sv) %>%
contrasts.fit(vf.cell.pos.cont.mat) %>%
eBayes()
vf.cell.pos.eb.tidy <- tidy(vf.cell.pos.eb) %>%
mutate(
adj_pval = p.adjust(p.value, method = "bonferroni"),
FC = 2 ^ estimate,
change_in_vpa = ifelse(FC < 1, "down", "up")
) %>%
rename(compound_short = gene)
vf.cell.pos.eb.tidy %>%
ggplot(aes(estimate, -log10(adj_pval))) +
geom_point(size = 2, alpha = 0.5) +
geom_hline(linetype = "dashed", color = "#009E73", yintercept = -log10(0.05)) +
geom_vline(linetype = "dashed", color = "#CC79A7", xintercept = log2(1.2)) +
geom_vline(linetype = "dashed", color = "#CC79A7", xintercept = log2(1/1.2)) +
xlim(-2.5, 2.5) +
xlab("log2(FC)") +
ylab("-log10(adjusted p-value)") +
ggtitle("Volcano plot\nVPA + FA / Cells / Positive Mode")
vf.cell.pos.hits <- vf.cell.pos.eb.tidy %>%
filter(adj_pval < 0.05 & (FC > 1.2 | FC < 1/1.2)) %>%
inner_join(vf.cell.pos.compound.info, by = "compound_short")
table(vf.cell.pos.hits$term)
FA_diff vpa_highFA vpa_lowFA
0 1 2
sort(unique(vf.cell.pos.hits$compound_full))
[1] "D-Sorbitol" "Proline"
vf.cell.pos.hits.tally2 <- vf.cell.pos.hits %>%
group_by(compound_short, compound_full) %>%
count() %>%
filter(n == 2)
vf.cell.pos.lowFA.hits <- vf.cell.pos.hits %>%
filter(term == "vpa_lowFA" & !(compound_short %in% vf.cell.pos.hits.tally2$compound_short))
vf.cell.pos.highFA.hits <- vf.cell.pos.hits %>%
filter(term == "vpa_highFA" & !(compound_short %in% vf.cell.pos.hits.tally2$compound_short))
vf.cell.pos.both.hits <- vf.cell.pos.hits %>%
filter(compound_short %in% vf.cell.pos.hits.tally2$compound_short) %>%
arrange(compound_short, term)
vf.cell.pos.hits
# A tibble: 3 x 14
compound_short term estimate statistic p.value lod adj_pval FC
<chr> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 hVPA_FApC18 vpa_~ 1.38 5.41 2.34e-5 2.78 0.00999 2.59
2 hVPA_FApC69 vpa_~ -1.23 -4.97 6.45e-5 1.83 0.0275 0.425
3 hVPA_FApC18 vpa_~ 1.74 5.86 8.28e-6 3.76 0.00353 3.33
# ... with 6 more variables: change_in_vpa <chr>, compound_full <chr>,
# formula <chr>, mass <dbl>, rt <dbl>, cas_id <chr>
### Plotting ###
vf.cell.pos.gathered <- vf.cell.pos.noNA %>%
filter(Group == "sample") %>%
bind_cols(vf.cell.pos.surr.var) %>%
select(Samples, VPA, FA, S1, starts_with("hVPA_FApC")) %>%
gather(key = "Compound", value = "Abundance", hVPA_FApC1:hVPA_FApC99)
vf.cell.pos.nested <- vf.cell.pos.gathered %>%
group_by(Compound) %>%
nest() %>%
mutate(model = map(data, ~lm(Abundance ~ S1, data = .))) %>%
mutate(augment_model = map(model, augment))
vf.cell.pos.modSV.resid <- vf.cell.pos.nested %>%
unnest(data, augment_model) %>%
select(Samples, VPA, FA, Compound, .resid) %>%
spread(Compound, .resid)
vf.cell.pos.modSV.resid %>%
select(Samples:FA, one_of(unique(vf.cell.pos.hits$compound_short))) %>%
HeatmapPrepAlt("hVPA_FApC") %>%
t() %>%
heatmaply(
colors = viridis(n = 10, option = "magma"),
xlab = "Samples", ylab = "Compounds",
main = "Statistically significant compounds\nVPA + FA HILIC / Cells / Positive Mode",
margins = c(50, 50, 75, 30),
k_col = 2, k_row = 2,
labRow = unique(vf.cell.pos.hits$compound_full)
)
### PCA - cleaned data ###
vf.cell.pos.modSV.pca <- vf.cell.pos.modSV.resid %>%
select(starts_with("hVPA_FApC")) %>%
mutate_all(scale, center = TRUE, scale = FALSE) %>%
as.matrix() %>%
prcomp()
vf.cell.pos.modSV.pca.x <- as.data.frame(vf.cell.pos.modSV.pca$x)
row.names(vf.cell.pos.modSV.pca.x) <- vf.cell.pos.modSV.resid$Samples
vf.cell.pos.modSV.pca.x <- vf.cell.pos.modSV.pca.x %>%
bind_cols(vf.cell.pos.modSV.resid %>% select(VPA:FA))
vf.cell.pos.modSV.pca.x %>%
ggplot(aes(x = PC1, y = PC2, color = VPA, shape = FA)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC1 (66.4% Var)") +
ylab("PC2 (12.5% Var)")
vf.cell.pos.modSV.pca.x %>%
ggplot(aes(x = PC3, y = PC4, color = VPA, shape = FA)) +
geom_point(size = 4, alpha = 0.8) +
xlab("PC3 (8.1% Var)") +
ylab("PC4 (3.1% Var)")
# sample prep
vf.med.neg.smpl.data <- vf.med.neg.noNA %>%
filter(Group == "sample") %>%
unite("Treatment", VPA:FA, sep = "_")
vf.med.neg.data.for.sva <- as.matrix(
vf.med.neg.smpl.data[, which(
colnames(vf.med.neg.smpl.data) == "hVPA_FAnM10"
):ncol(vf.med.neg.smpl.data)]
)
row.names(vf.med.neg.data.for.sva) <- vf.med.neg.smpl.data$Samples
vf.med.neg.data.for.sva <- t(vf.med.neg.data.for.sva)
# pheno prep
vf.med.neg.data.pheno <- as.data.frame(vf.med.neg.smpl.data[, 5:6])
row.names(vf.med.neg.data.pheno) <- vf.med.neg.smpl.data$Samples
# sva calculation
vf.med.neg.mod.vf <- model.matrix(~ 0 + as.factor(Treatment), data = vf.med.neg.data.pheno)
vf.med.neg.mod0 <- model.matrix(~ 1, data = vf.med.neg.data.pheno)
set.seed(2018)
num.sv(vf.med.neg.data.for.sva, vf.med.neg.mod.vf, method = "be")
[1] 0
set.seed(2018)
num.sv(vf.med.neg.data.for.sva, vf.med.neg.mod.vf, method = "leek")
[1] 0
set.seed(2018)
vf.med.neg.sv <- sva(vf.med.neg.data.for.sva, vf.med.neg.mod.vf, vf.med.neg.mod0)
No significant surrogate variables
# extract the surrogate variables
colnames(vf.med.neg.mod.vf) <- c("cntrl", "fa_only", "vpa_only", "fa_and_vpa")
# combine the full model matrix and the surrogate variables into one
vf.med.neg.design.sv <- vf.med.neg.mod.vf
vf.med.neg.cont.mat <- makeContrasts(
vpa_lowFA = vpa_only - cntrl,
vpa_highFA = fa_and_vpa - fa_only,
FA_diff = (fa_and_vpa - fa_only) - (vpa_only - cntrl),
levels = c("cntrl", "fa_only", "vpa_only", "fa_and_vpa")
)
# fit the model/design matrix
vf.med.neg.eb <- vf.med.neg.data.for.sva %>%
lmFit(vf.med.neg.design.sv) %>%
contrasts.fit(vf.med.neg.cont.mat) %>%
eBayes()
# pull out the results for each metabolite for each comparison
vf.med.neg.eb.tidy <- tidy(vf.med.neg.eb) %>%
mutate(
adj_pval = p.adjust(p.value, method = "bonferroni"),
FC = 2 ^ estimate,
change_in_vpa = ifelse(FC < 1, "down", "up")
) %>%
rename(compound_short = gene)
# volcano plot
vf.med.neg.eb.tidy %>%
ggplot(aes(estimate, -log10(adj_pval))) +
geom_point(size = 2, alpha = 0.5) +
geom_hline(linetype = "dashed", color = "#009E73", yintercept = -log10(0.05)) +
geom_vline(linetype = "dashed", color = "#CC79A7", xintercept = log2(1.2)) +
geom_vline(linetype = "dashed", color = "#CC79A7", xintercept = log2(1/1.2)) +
xlab("log2(FC)") +
ylab("-log10(adjusted p-value)") +
ggtitle("Volcano plot\nVPA + FA / meds / Negative Mode")
# select statistically significant hits with a certain FC:
vf.med.neg.hits <- vf.med.neg.eb.tidy %>%
filter(adj_pval < 0.05 & (FC > 1.2 | FC < 1/1.2)) %>%
inner_join(vf.med.neg.compound.info, by = "compound_short")
# how many metabolites are significant across the different contrats
table(vf.med.neg.hits$term)
FA_diff vpa_highFA vpa_lowFA
0 2 1
# significant metabolites
sort(unique(vf.med.neg.hits$compound_full))
[1] "Caprylic Acid" "Taurine"
vf.med.neg.hits
# A tibble: 3 x 14
compound_short term estimate statistic p.value lod adj_pval FC
<chr> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 hVPA_FAnM21 vpa_~ 5.48 69.1 5.78e-29 56.5 9.02e-27 44.8
2 hVPA_FAnM14 vpa_~ 0.519 6.47 1.12e- 6 3.97 1.74e- 4 1.43
3 hVPA_FAnM21 vpa_~ 5.44 68.5 7.15e-29 56.3 1.12e-26 43.3
# ... with 6 more variables: change_in_vpa <chr>, compound_full <chr>,
# formula <chr>, mass <dbl>, rt <dbl>, cas_id <chr>
# sample prep
vf.med.pos.smpl.data <- vf.med.pos.noNA %>%
filter(Group == "sample") %>%
unite("Treatment", VPA:FA, sep = "_")
vf.med.pos.data.for.sva <- as.matrix(
vf.med.pos.smpl.data[, which(
colnames(vf.med.pos.smpl.data) == "hVPA_FApM1"
):ncol(vf.med.pos.smpl.data)]
)
row.names(vf.med.pos.data.for.sva) <- vf.med.pos.smpl.data$Samples
vf.med.pos.data.for.sva <- t(vf.med.pos.data.for.sva)
vf.med.pos.data.pheno <- as.data.frame(vf.med.pos.smpl.data[, 5:6])
row.names(vf.med.pos.data.pheno) <- vf.med.pos.smpl.data$Samples
vf.med.pos.mod.vf <- model.matrix(~ 0 + as.factor(Treatment), data = vf.med.pos.data.pheno)
vf.med.pos.mod0 <- model.matrix(~ 1, data = vf.med.pos.data.pheno)
set.seed(2018)
num.sv(vf.med.pos.data.for.sva, vf.med.pos.mod.vf, method = "be")
[1] 0
set.seed(2018)
num.sv(vf.med.pos.data.for.sva, vf.med.pos.mod.vf, method = "leek")
[1] 0
set.seed(2018)
vf.med.pos.sv <- sva(vf.med.pos.data.for.sva, vf.med.pos.mod.vf, vf.med.pos.mod0)
No significant surrogate variables
colnames(vf.med.pos.mod.vf) <- c("cntrl", "fa_only", "vpa_only", "fa_and_vpa")
vf.med.pos.design.sv <- vf.med.pos.mod.vf
vf.med.pos.cont.mat <- makeContrasts(
vpa_lowFA = vpa_only - cntrl,
vpa_highFA = fa_and_vpa - fa_only,
FA_diff = (fa_and_vpa - fa_only) - (vpa_only - cntrl),
levels = c("cntrl", "fa_only", "vpa_only", "fa_and_vpa")
)
vf.med.pos.eb <- vf.med.pos.data.for.sva %>%
lmFit(vf.med.pos.design.sv) %>%
contrasts.fit(vf.med.pos.cont.mat) %>%
eBayes()
vf.med.pos.eb.tidy <- tidy(vf.med.pos.eb) %>%
mutate(
adj_pval = p.adjust(p.value, method = "bonferroni"),
FC = 2 ^ estimate,
change_in_vpa = ifelse(FC < 1, "down", "up")
) %>%
rename(compound_short = gene)
# volcano plot
vf.med.pos.eb.tidy %>%
ggplot(aes(estimate, -log10(adj_pval))) +
geom_point(size = 2, alpha = 0.5) +
geom_hline(linetype = "dashed", color = "#009E73", yintercept = -log10(0.05)) +
geom_vline(linetype = "dashed", color = "#CC79A7", xintercept = log2(1.2)) +
geom_vline(linetype = "dashed", color = "#CC79A7", xintercept = log2(1/1.2)) +
xlab("log2(FC)") +
ylab("-log10(adjusted p-value)") +
ggtitle("Volcano plot\nVPA + FA / meds / posative Mode")
# select statistically significant hits with a certain FC:
vf.med.pos.hits <- vf.med.pos.eb.tidy %>%
filter(adj_pval < 0.05 & (FC > 1.2 | FC < 1/1.2)) %>%
inner_join(vf.med.pos.compound.info, by = "compound_short")
# how many metabolites are significant across the different contrats
table(vf.med.pos.hits$term)
FA_diff vpa_highFA vpa_lowFA
0 0 0
sessionInfo()
R version 3.5.1 (2018-07-02)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 7 x64 (build 7601) Service Pack 1
Matrix products: default
locale:
[1] LC_COLLATE=English_United States.1252
[2] LC_CTYPE=English_United States.1252
[3] LC_MONETARY=English_United States.1252
[4] LC_NUMERIC=C
[5] LC_TIME=English_United States.1252
attached base packages:
[1] stats graphics grDevices utils datasets methods base
other attached packages:
[1] bindrcpp_0.2.2 ggridges_0.5.1 biobroom_1.12.1
[4] broom_0.5.0 limma_3.36.5 sva_3.28.0
[7] BiocParallel_1.14.2 genefilter_1.62.0 mgcv_1.8-25
[10] nlme_3.1-137 heatmaply_0.15.2 viridis_0.5.1
[13] viridisLite_0.3.0 plotly_4.8.0 GGally_1.4.0
[16] cowplot_0.9.3 forcats_0.3.0 stringr_1.3.1
[19] dplyr_0.7.8 purrr_0.2.5 readr_1.1.1
[22] tidyr_0.8.2 tibble_1.4.2 ggplot2_3.1.0
[25] tidyverse_1.2.1
loaded via a namespace (and not attached):
[1] colorspace_1.3-2 class_7.3-14 modeltools_0.2-22
[4] mclust_5.4.1 rprojroot_1.3-2 rstudioapi_0.8
[7] flexmix_2.3-14 bit64_0.9-7 fansi_0.4.0
[10] AnnotationDbi_1.42.1 mvtnorm_1.0-8 lubridate_1.7.4
[13] xml2_1.2.0 splines_3.5.1 codetools_0.2-15
[16] robustbase_0.93-3 knitr_1.20 jsonlite_1.5
[19] annotate_1.58.0 cluster_2.0.7-1 kernlab_0.9-27
[22] shiny_1.2.0 compiler_3.5.1 httr_1.3.1
[25] backports_1.1.2 assertthat_0.2.0 Matrix_1.2-15
[28] lazyeval_0.2.1 cli_1.0.1 later_0.7.5
[31] htmltools_0.3.6 tools_3.5.1 gtable_0.2.0
[34] glue_1.3.0 reshape2_1.4.3 Rcpp_1.0.0
[37] Biobase_2.40.0 cellranger_1.1.0 trimcluster_0.1-2.1
[40] gdata_2.18.0 crosstalk_1.0.0 iterators_1.0.10
[43] fpc_2.1-11.1 rvest_0.3.2 mime_0.6
[46] gtools_3.8.1 XML_3.98-1.16 dendextend_1.9.0
[49] DEoptimR_1.0-8 MASS_7.3-51.1 scales_1.0.0
[52] TSP_1.1-6 promises_1.0.1 hms_0.4.2
[55] parallel_3.5.1 RColorBrewer_1.1-2 yaml_2.2.0
[58] memoise_1.1.0 gridExtra_2.3 reshape_0.8.8
[61] stringi_1.2.4 RSQLite_2.1.1 gclus_1.3.1
[64] S4Vectors_0.18.3 foreach_1.4.4 seriation_1.2-3
[67] caTools_1.17.1.1 BiocGenerics_0.26.0 matrixStats_0.54.0
[70] rlang_0.3.0.1 pkgconfig_2.0.2 prabclus_2.2-6
[73] bitops_1.0-6 evaluate_0.12 lattice_0.20-38
[76] bindr_0.1.1 labeling_0.3 htmlwidgets_1.3
[79] bit_1.1-14 tidyselect_0.2.5 plyr_1.8.4
[82] magrittr_1.5 R6_2.3.0 IRanges_2.14.12
[85] gplots_3.0.1 DBI_1.0.0 pillar_1.3.0
[88] haven_1.1.2 whisker_0.3-2 withr_2.1.2
[91] survival_2.43-1 RCurl_1.95-4.11 nnet_7.3-12
[94] modelr_0.1.2 crayon_1.3.4 utf8_1.1.4
[97] KernSmooth_2.23-15 rmarkdown_1.10 grid_3.5.1
[100] readxl_1.1.0 data.table_1.11.8 blob_1.1.1
[103] digest_0.6.18 diptest_0.75-7 webshot_0.5.1
[106] xtable_1.8-3 httpuv_1.4.5 stats4_3.5.1
[109] munsell_0.5.0 registry_0.5